The Python micro framework for building web applications.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

Mamba SSM architecture

End-to-End Speech Processing Toolkit

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/

Rainbow: Combining Improvements in Deep Reinforcement Learning

TensorFlow Code for paper "Efficient Neural Architecture Search via Parameter Sharing"

Controllable and fast Text-to-Speech for over 7000 languages!

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

MLNLP社区用来更好进行论文搜索的工具。Fully-automated scripts for collecting AI-related papers

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

Really Fast End-to-End Jax RL Implementations

This project provides a stock market environment using OpenGym with Deep Q-learning and Policy Gradient.

Inverse RL algorithms (APP, MaxEnt, GAIL, VAIL)

Noise Conditional Score Networks (NeurIPS 2019, Oral)

MelGAN vocoder (compatible with NVIDIA/tacotron2)

Awesome Quadrupedal Robots

⏩ Generating speech in a single forward pass without any attention!

The official code for "One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)"

Reflexion: an autonomous agent with dynamic memory and self-reflection

RAG-GPT, leveraging LLM and RAG technology, learns from user-customized knowledge bases to provide contextually relevant answers for a wide range of queries, ensuring rapid and accurate information…

Official implementation of CVPR23 paper "Diffusion-based Generation, Optimization, and Planning in 3D Scenes"

Anonymous Multi-Agent Path Finding (MAPF) with Conflict-Based Search and Space-Time A*